Pix2struct Base Table2html

🚀 pix2struct-base-table2html

Transform table images into HTML! This model efficiently parses table images, conducts OCR, and outputs them in HTML format.

🚀 Quick Start

You can try the demo app which combines both table detection and recognition!

✨ Features

This model takes a table image as input and outputs HTML. It parses the image, performs optical character recognition (OCR), and structure recognition to convert it into HTML format.

• Input Requirement: The model expects an image containing only a table. If the table is embedded in a document, you should first use a table detection model (e.g., Microsoft's Table Transformer model) to extract it.
• Fine - Tuning Details: The model is fine - tuned from the Pix2Struct base model with a max_patch_length of 1024 and a max_generation_length of 1024. For inference, the max_patch_length should generally not be changed, but the generation_length can be adjusted.
• Training Datasets: The model has been trained using two datasets: MMTab and PubTabNet.

📦 Installation

Since this is a model from the transformers library, you need to install the transformers library. You can install it using the following command:

pip install transformers

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoProcessor, Pix2StructForConditionalGeneration
from PIL import Image
import requests
from io import BytesIO

# Load model and processor
device = "cuda" if torch.cuda.is_available() else "cpu"
processor = AutoProcessor.from_pretrained("KennethTM/pix2struct-base-table2html")
model = Pix2StructForConditionalGeneration.from_pretrained("KennethTM/pix2struct-base-table2html")
model.to(device)
model.eval()

# Load example image from URL
url = "https://huggingface.co/KennethTM/pix2struct-base-table2html/resolve/main/example_recog_1.jpg"
response = requests.get(url)
image = Image.open(BytesIO(response.content))

# Run model inference
encoding = processor(image, return_tensors="pt", max_patches=1024)
with torch.inference_mode():
    flattened_patches = encoding.pop("flattened_patches").to(device)
    attention_mask = encoding.pop("attention_mask").to(device)
    predictions = model.generate(flattened_patches=flattened_patches, attention_mask=attention_mask, max_new_tokens=1024)

predictions_decoded = processor.tokenizer.batch_decode(predictions, skip_special_tokens=True)

# Show predictions as text
print(predictions_decoded[0])

Example Image

Model HTML Output for Example Image

<table border="1" cellspacing="0">
 <tr>
  <th>
   Rank
  </th>
  <th>
   Lane
  </th>
  <th>
   Name
  </th>
  <th>
   Nationality
  </th>
  <th>
   Time
  </th>
  <th>
   Notes
  </th>
 </tr>
 <tr>
  <td>
  </td>
  <td>
   4
  </td>
  <td>
   Michael Phelps
  </td>
  <td>
   United States
  </td>
  <td>
   51.25
  </td>
  <td>
   OR
  </td>
 </tr>
 <tr>
  <td>
  </td>
  <td>
   3
  </td>
  <td>
   Ian Crocker
  </td>
  <td>
   United States
  </td>
  <td>
   51.29
  </td>
  <td>
  </td>
 </tr>
 <tr>
  <td>
  </td>
  <td>
   5
  </td>
  <td>
   Andriy Serdinov
  </td>
  <td>
   Ukraine
  </td>
  <td>
   51.36
  </td>
  <td>
   EU
  </td>
 </tr>
 <tr>
  <td>
   4
  </td>
  <td>
   1
  </td>
  <td>
   Thomas Rupprath
  </td>
  <td>
   Germany
  </td>
  <td>
   52.27
  </td>
  <td>
  </td>
 </tr>
 <tr>
  <td>
   5
  </td>
  <td>
   6
  </td>
  <td>
   Igor Marchenko
  </td>
  <td>
   Russia
  </td>
  <td>
   52.32
  </td>
  <td>
  </td>
 </tr>
 <tr>
  <td>
   6
  </td>
  <td>
   2
  </td>
  <td>
   Gabriel Mangabeira
  </td>
  <td>
   Brazil
  </td>
  <td>
   52.34
  </td>
  <td>
  </td>
 </tr>
 <tr>
  <td>
   7
  </td>
  <td>
   8
  </td>
  <td>
   Duje Draganja
  </td>
  <td>
   Croatia
  </td>
  <td>
   52.46
  </td>
  <td>
  </td>
 </tr>
 <tr>
  <td>
   8
  </td>
  <td>
   7
  </td>
  <td>
   Geoff Huegill
  </td>
  <td>
   Australia
  </td>
  <td>
   52.56
  </td>
  <td>
  </td>
 </tr>
</table>

Rendered HTML Table

📄 License

This project is licensed under the MIT license.